© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24078
    Prev
    Next
    INDEX
    Explanations

    France

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <0x96>
    0.66
    忔
    0.64
    ipzig
    0.62
    ვილი
    0.62
     nhất
    0.61
     omitting
    0.61
    အချိန်
    0.61
    <0x99>
    0.60
     abundances
    0.60
     निवासी
    0.60
    POSITIVE LOGITS
    0
    1.03
    3
    1.03
    to
    0.98
    ↵
    0.90
    4
    0.90
    EM
    0.89
    MS
    0.89
     in
    0.85
    2
    0.84
    ك
    0.84
    Activations Density 0.007%

    No Known Activations